Environment Sound Classification Using Multiple Feature Channels and Attention Based Deep Convolutional Neural Network

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use attention modules that perform channel and spatial attention together. We use the mix-up data augmentation technique to further boost performance. Our model is able to achieve state-of-the-art performance on three benchmark environment sound classification datasets, i.e. the UrbanSound8K (97.52%), ESC-10 (94.75%) and ESC-50 (87.45%).